Action recognition based on principal geodesic analysis

In this paper, we consider the action recognition problem based on geometrical structure. Our method uses a low dimensional structure on the Grassmannian manifold to represent video sequences, by utilizing the linear structure of the tangent space. This approach can be divided into a training (off-line computing) stage and testing (on-line computing) stage, and makes the recognition algorithm scalable to large data sets. We test the proposed method on several benchmark data sets. The result shows that the new approach takes less computation compared to previous work based on the same geometrical assumption, and has similar or even higher recognition accuracy.